Strong Clutter Background Research Articles

A Multicomponent Linear Frequency Modulation Signal-Separation Network for Multi-Moving-Target Imaging in the SAR-Ground-Moving-Target Indication System

Multi-moving-target imaging in a synthetic aperture radar (SAR) system poses a significant challenge owing to target defocusing and being contaminated by strong background clutter. Aiming at this problem, a new deep-convolutional-neural-network (CNN)-assisted method is proposed for multi-moving-target imaging in a SAR-GMTI system. The multi-moving-target signal can be modeled by a multicomponent LFM signal with additive perturbation. A fully convolutional network named MLFMSS-Net was designed based on an encoder–decoder architecture to extract the most-energetic LFM signal component from the multicomponent LFM signal in the time domain. Without prior knowledge of the target number, an iterative signal-separation framework based on the well-trained MLFMSS-Net is proposed to separate the multi-moving-target signal into multiple LFM signal components while eliminating the residual clutter. It works well, exhibiting high imaging robustness and low dependence on the system parameters, making it a suitable solution for practical imaging applications. Consequently, a well-focused multi-moving-target image can be obtained by parameter estimation and secondary azimuth compression for each separated LFM signal component. The simulations and experiments on both airborne and spaceborne SAR data showed that the proposed method is superior to traditional imaging methods in both imaging quality and efficiency.

Feature Enhancement Using Multi-Baseline SAR Interferometry-Correlated Synthesis Images for Power Transmission Tower Detection in Mountain Layover Area

The detection performance of power transmission towers in mountainous areas using SAR amplitude images is obviously influenced by the strong layover background (mainly including vegetation and soil) clutter interference around the towers. In this paper, power transmission tower detection in a mountainous layover area, using single-baseline SAR interferometry coherence images, which show better feature enhancement effectiveness compared to SAR amplitude images, is presented. Moreover, a novel feature enhancement method, that of generating multi-baseline SAR interferometry-correlated synthesis images for power transmission tower detection in a mountain layover area, is proposed. It demonstrates better feature enhancement (layover background cluster suppression) than that using single-baseline SAR interferometry coherence images. Theoretical analysis illustrates that the mountainous layover background clutter interference can be suppressed in the proposed single-baseline/multi-baseline SAR interferometry-correlated synthesis image. Experiments including over 12 repeat-pass TerraSAR-X staring spotlight mode acquisitions were conducted, and the results demonstrate that the detection performance with the use of multi-baseline SAR interferometry-correlated synthesis images showed an improvement of more than 43.6%, compared with the traditional method of using SAR amplitude images when benchmark deep learning-based detectors are used, i.e., Faster RCNN and YOLOv7.

Detection of infrared small target based on background subtraction local contrast measure and Gaussian structural similarity

Infrared (IR) small target detection, especially in a complex background, continues to present challenges in the low false alarm rate and high robustness. In this paper, a background subtraction local contrast measure (BSLCM) and Gaussian structural similarity (GSS) integrated structural model is proposed to detect IR small target. In the proposed model, BSLCM is used to suppress the complex background and enhance the target. GSS calculation is conducted to eliminate the high-brightened background residual and noise further. To evaluate the performance of the proposed method, real IR sequences and seven state-of-the-art (SOTA) methods were adopted. The results demonstrated that the BSLCM can suppress all types of strong background clutter and enhance the true target effectively.

Effective and robust infrared small target detection based on directional improved structure tensor

Small target detection under complicated background is a research hotspot and challenging problem. To increase the ability of small target detection under complicated background, a simple but effective target detection approach based on directional improved structure tensor is designed. Firstly, considering that small target region will be omni-directional while background edge clutters will tend to expand in some specific directions, the directional structure tensor (DST) is constructed by incorporating eight-direction filter template. Then, the directional positive small eigenvalue of the structure tensor (DPSTSE) is computed to effectively perceive and locate the junctions of small target and surrounding background in all directions. Finally, the DPSTSE maps in all directions are integrated together to distinguish small targets from strong background clutter. Experiments illustrate that the presented method is better than some advanced algorithms in clutter suppression ability and target detection effect. Moreover, the presented method has high computational efficiency and potential for real-time processing.

Adaptive Support-Driven Sparse Recovery STAP Method with Subspace Penalty

Detecting a moving target is an attractive topic in many fields, such as remote sensing. Space-time adaptive processing (STAP) plays a key role in detecting moving targets in strong clutter backgrounds for airborne early warning radar systems. However, STAP suffers serious clutter suppression performance loss when the number of training samples is insufficient due to the inhomogeneous clutter environment. In this article, an efficient sparse recovery STAP algorithm is proposed. First, inspired by the relationship between multiple sparse Bayesian learning (M-SBL) and subspace-based hybrid greedy algorithms, a new optimization objective function based on a subspace penalty is established. Second, the closed-form solution of each minimization step is obtained through the alternating minimization algorithm, which can guarantee the convergence of the algorithm. Finally, a restart strategy is used to adaptively update the support, which reduces the computational complexity. Simulation results show that the proposed algorithm has excellent performance in clutter suppression, convergence speed and running time with insufficient training samples.

A Generalized Low-Rank Double-Tensor Nuclear Norm Completion Framework for Infrared Small Target Detection

Infrared small target detection is a research hotspot in computer vision technology that plays an important role in infrared early warning systems. Specifically, infrared images with strong background clutter and noise pose a challenge to target detection technology. In this article, we propose a method for infrared small target detection based on the double nuclear norm and ring-structural elements over a generalized tensor framework. We use the double nuclear norm instead of the traditional single nuclear norm as the relaxation of the rank function, which solves the problem that the suboptimal solution deviates from the original solution and better approaches the rank minimization. In addition, we use weighted ring structural elements instead of traditional structural elements to make better use of the target information and its surrounding background. Experiments on six sequences of real images show that the proposed method can enhance the target and suppress the background effectively, and ensure a high detection probability and a low false alarm rate.

A Robust Dual-Platform GMTI Method against Nonuniform Clutter

The ground moving-target indication (GMTI) technique can detect civil and military moving targets, which means that this technique has received much attention. Strong clutter background suppression is one of the critical problems in this application. However, the detection performance in heterogeneous environment can be degraded due to the inaccurate estimation of the clutter covariance matrix (CCM). In this paper, we propose a robust GMTI method using a spaceborne dual-platform synthetic aperture radar (SAR) system, which can obtain highly accurate CCM in nonuniform clutter. Firstly, the accurate CCM is estimated based on the SAR image obtained by the former platform. Then, space–time adaptive processing (STAP) is carried out using the obtained the CCM. Finally, the detection threshold is set according to the estimated CCM and detection is executed accurately. Compared with the traditional CCM estimation method in STAP using the clutter nearby the cell under test, this method directly estimates the CCM using the clutter of the cell under test, which can avoid CCM estimation mistakes in heterogeneous clutter environment. The clutter can be whitened and depressed more effectively. Additionally, with the accurate threshold acquired from the CCM, the detection probability can be effectively improved under a certain false-alarm criterion. Based on simulation data, GMTI experiments in a heterogeneous environment such as clutter with strong pollution, junction zone of hot and cold clutter, and clutter with nonuniform power are carried out; the results show that the moving targets can be effectively detected with the proposed method.

A Novel SAR Imaging Method Based on Morphological Component Analysis

Clutter suppression plays an important role in a synthetic aperture radar (SAR) system. The conventional SAR imaging methods are useful for distinguishing the echo signal and noise, but cannot separate the target signal from background clutter. Inspired by the signal separation ability of morphological component analysis (MCA), a novel SAR imaging method based on MCA is proposed to suppress the strong background clutter. In the new model, the SAR echo is considered as a linear superposition of target signal, clutter signal, and noise. According to different characteristics of morphological components, clutter dictionary and target dictionary are constructed to sparsely represent the clutter component and target component, respectively. Then, the MCA method based on the sparse representation and morphological diversity of signals is employed to decompose the SAR echo into the target signal, clutter signal, and noise. Finally, the separated target signal is processed to obtain the ultimate SAR image. Experimental results from simulated and real SAR data are provided to demonstrate the effectiveness of the proposed method.

Context-Unsupervised Adversarial Network for Video Sensors.

Foreground object segmentation is a crucial first step for surveillance systems based on networks of video sensors. This problem in the context of dynamic scenes has been widely explored in the last two decades, but it still has open research questions due to challenges such as strong shadows, background clutter and illumination changes. After years of solid work based on statistical background pixel modeling, most current proposals use convolutional neural networks (CNNs) either to model the background or to make the foreground/background decision. Although these new techniques achieve outstanding results, they usually require specific training for each scene, which is unfeasible if we aim at designing software for embedded video systems and smart cameras. Our approach to the problem does not require specific context or scene training, and thus no manual labeling. We propose a network for a refinement step on top of conventional state-of-the-art background subtraction systems. By using a statistical technique to produce a rough mask, we do not need to train the network for each scene. The proposed method can take advantage of the specificity of the classic techniques, while obtaining the highly accurate segmentation that a deep learning system provides. We also show the advantage of using an adversarial network to improve the generalization ability of the network and produce more consistent results than an equivalent non-adversarial network. The results provided were obtained by training the network on a common database, without fine-tuning for specific scenes. Experiments on the unseen part of the CDNet database provided 0.82 a F-score, and 0.87 was achieved for LASIESTA databases, which is a database unrelated to the training one. On this last database, the results outperformed by 8.75% those available in the official table. The results achieved for CDNet are well above those of the methods not based on CNNs, and according to the literature, among the best for the context-unsupervised CNNs systems.

Multichannel SAR Moving Target Detection via RPCA-Net

Ground moving target indication (GMTI), as a challenging task for synthetic aperture radar (SAR) systems, keeps drawing considerable attention. Robust principal component analysis (RPCA) aiming at separating low-rank and sparse components has been successfully employed in SAR systems for GMTI recently. However, its practical application is limited by the heavy computational burden as well as the requirement of manual parameter modification. To cope with this problem, a fast and free of presetting parameters RPCA network (RPCA-Net) is proposed for SAR-GMTI under strong clutter background. In the proposed method, a novel RPCA model is first introduced, where not only the low-rank and sparse terms but also the errors in practical SAR systems are taken into account. Moreover, the low-rank factorization plus scaled gradient descent (ScaledGD) is also employed to acquire low-rank clutter background rather than singular value decomposition (SVD). Then, we parameterize our proposed RPCA model and unfold it as a feedforward neural network (FNN) to acquire the iterative parameters through backpropagation. Compared to the GMTI methods based on traditional RPCA models, our proposed RPCA-Net can provide a higher detection ability and faster convergence without presetting parameters empirically. Experiments on two groups of measured data collected by airborne SAR systems validate the superior performance of the proposed RPCA-Net.

Geodesic Normal Coordinate-Based Manifold Filtering for Target Detection

Recently, the matrix information geometry (MIG) detector, which characterizes sample data as a Hermitian positive definite (HPD) matrix located on the HPD manifold, was rapidly developed and demonstrated extraordinary performance in numerous applications, especially in heterogeneous clutter backgrounds. In this paper, the geodesic normal coordinate (GNC)-based manifold filter is proposed to improve the detection performance of the MIG detector in strong clutter backgrounds. Using the GNC system, the distribution of target echoes and clutter on the high-dimensional manifold can be visualized and analyzed. Moreover, by exploiting the information concerning the distribution of matrices, the manifold filter is proposed to enhance target echoes and suppress strong clutter. Then, the manifold-filter-based MIG detector is designed, and its superiority is theoretically analyzed. The actual clutter data is utilized to verify the effectiveness of the proposed method. The results show that the proposed manifold filter achieves a signal-to-clutter ratio improvement of more than 5 dB over the existing MIG detectors.

Infrared Small Target Detection Based on Smoothness Measure and Thermal Diffusion Flowmetry

Infrared (IR) small target detection in a complex environment has become a hot topic. Due to the dim intensity and small scale of the target and the strong background clutter, the existing algorithms cannot achieve satisfactory results, namely poor detection performance and poor real-time performance. In this letter, a new real-time small target detection algorithm based on smoothness measure and thermal diffusion (STD) is proposed. First, the smoothness measure is proposed to extract smoothness features of small targets and suppress the clutter background. Then, we improve the existing thermal diffusion equation and design a thermal diffusion operator to extract the target’s thermal diffusion feature. The operator will further enhance the small and dim target’s energy. Finally, the fusion result image—in which the background is suppressed and the target is enhanced—is acquired after combining smoothness and thermal diffusion flowmetry. The experimental results demonstrate that the detection speed of the proposed algorithm is at least four times faster than that of existing algorithms under the same detection conditions. In addition, the proposed algorithm can achieve outstanding detection performance for IR images with different types of complex backgrounds and targets’ sizes within <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$7\times7$ </tex-math></inline-formula> .

Extremely Robust Remote-Target Detection Based on Carbon Dioxide-Double Spikes in Midwave Spectral Imaging

Infrared ship-target detection for sea surveillance from the coast is very challenging because of strong background clutter, such as cloud and sea glint. Conventional approaches utilize either spatial or temporal information to reduce false positives. This paper proposes a completely different approach, called carbon dioxide-double spike (CO2-DS) detection in midwave spectral imaging. The proposed CO2-DS is based on the spectral feature where a hot CO2 emission band is broader than that which is absorbed by normal atmospheric CO2, which generates CO2-double spikes. A directional-mean subtraction filter (D-MSF) detects each CO2 spike, and final targets are detected by joint analysis of both types of detection. The most important property of CO2-DS detection is that it generates an extremely low number of false positive caused by background clutter. Only the hot CO2 spike of a ship plume can penetrate atmosphere, and furthermore, there are only ship CO2 plume signatures in the double spikes of different spectral bands. Experimental results using midwave Fourier transform infrared (FTIR) in a remote sea environment validate the extreme robustness of the proposed ship-target detection.

DeepImaging: A Ground Moving Target Imaging Based on CNN for SAR-GMTI System

Imaging of ground multiple moving targets in a synthetic aperture radar (SAR) system is a challenging task due to the fact that targets are defocused owing to motions and contaminated by the strong background clutter. Motivated by recent advances in deep learning, a novel deep convolutional neural network (CNN)-based method, DeepImaging, is proposed for ground moving target imaging (GMTIm). Different from conventional imaging methods relying on the prior knowledge of imaging, the proposed DeepImaging is directly trained to learn an implicit imaging model of multiple moving targets. It is free of motion parameter estimation and iteration process. Then, the trained DeepImaging, as an imaging processor, can be applied to the SAR complex received data after clutter suppression to achieve the multiple moving target imaging and the residual clutter elimination simultaneously. Simulations and experiments on the Gotcha data show that the proposed method achieves significant improvements over existing state-of-the-art GMTIm methods in terms of imaging quality and efficiency.

Detection of Wind Turbines in Intertidal Areas Using SAR Polarimetry

The detection of wind turbines in a strong clutter background is analyzed at variance of polarimetric synthetic-aperture radar (SAR) configurations. The area of interest is the intertidal zone near Jiangsu, China and two detectors are used, the polarimetric notch filter (PNF) and a change detector that optimizes the ratio between covariance matrices. The detection performance is quantitatively analyzed using the receiver operating characteristic (ROC) curve, while the scattering mechanisms that characterize wind turbines are analyzed using the Yamaguchi decomposition. Experimental analysis shows that: 1) wind turbines result in a nontrivial scattering mechanism and 2) full-polarimetric measurements achieve the best detection performance independently of the two detectors.

Moving Target Detection in Multichannel SAR Framework using Adaptive Neuro Fuzzy Decisive Technique

Precise and efficacious detection of moving targets is a prominent task in on-going synthetic aperture radar (SAR) technique. The perception of moving object allows quite significant data about the situation under observation for both surveillance and intelligence activities. The task of accurately locating moving targets against strong background clutter in minimum of time is of utmost interest in the current research area. Fractional Fourier Transform (FrFT) concentrates the energy of the required chirp signal so that it can be well separated from the chirp like noise. The proposed SAR Moving Target Detection (MTD) process is based on the combination of FrFT with the adaptive-neuro fuzzy decisive technique. The correlation among the received signal and the FrFT of the received signal are computed which maximizes the required signal energy and applied to the adaptive-neuro fuzzy decisive module that detects the target location adaptively using the fuzzy linguistic rules. The simulation is performed by changing the number of targets, different Pulse repetition intervals, antenna turn velocity, iterations and the analysis is carried out based on the metrics, like detection time, missed target rate, and Mean Square Error (MSE), proving that the proposed Adaptive-Neuro Fuzzy-based MTD process detected the object in 5.0237 secs with a minimum missed target rate of 0.1210 and MSE of 23377.48.

Reduced Dimension STAP Based on Sparse Recovery in Heterogeneous Clutter Environments

For airborne-phased array radar systems, space-time adaptive processing (STAP) is supposed to be a crucial technique for improving target detection performance in the strong clutter background. However, practical application environments are always heterogeneous and have offered a severe challenge to the implementation of STAP. To address this reality, a data-dependent reduced dimension STAP approach based on sparse recovery (SR) is proposed in this paper. To take a full account of the heterogeneous environments, we consider the extremely heterogeneous case in which only one single snapshot is available. There is no doubt that, compared with the clutter covariance matrix (CCM) calculated directly by a single snapshot, the SR technique can provide a more accurate estimate. However, we should come to realize that this estimation is not accurate enough to adaptive processing according to the presented simulation results in lots of literature, and it has been demonstrated that the performance of traditional SR-based STAP degrades dramatically when only a snapshot is available. In the proposed approach, the CCM estimated by SR technique is utilized to design the reduced dimension transformation matrix rather than to calculate adaptive weights as the traditional SR-based STAP. The relatively accurate CCM can provide better support for the design of reduced dimension transformation matrix. From the simulation results, the proposed approach can achieve great performance of clutter suppression and target detection with only a single snapshot compared with several typical STAP algorithms. It is worthwhile pointing out that the proposed approach can also be applied when multiple snapshots are available and the performance improves with increasing number of available snapshots.

Space time adaptive processing based on sparse recovery and clutter reconstructing

For an airborne-phased array radar system, space-time adaptive processing (STAP) is supposed to be a crucial technique for improving its target detection performance in a strong clutter background. Here, the authors consider the extreme heterogeneous case, i.e. the number of available training samples is limited to one. With only one training sample, the sparse recovery (SR) technique is utilized to estimate the clutter patches in the angular-Doppler plane, i.e. the pair of Doppler frequency and spatial frequency corresponding to the grid in angular-Doppler plane is determined. Based on the observation that some clutter components may be missed for one secondary data sample, the clutter covariance matrix (CCM) is estimated through reconstructing some missed clutter components by utilising the symmetric property of clutter return. From the simulation results, the proposed approach can achieve great performance of clutter suppression with only one training sample compared with conventional SR-based STAP algorithms.

Dim small target detection based on high-order cumulant of motion estimation

To improve the detection ability of dim targets in strong clutter background, a new non-uniform correction method of ring perturbation in sequence images is proposed to remove the non-uniformity of images, and then the multi-frame cumulation technique is used to enhance the dim targets. Finally, on the basis of pre-processing, Poisson distribution is used to obtain candidate target images in advance, next use the high-order cumulant for further extract, and to process the detection results of the above two algorithms by “AND” operation to obtain the common candidate target points. With that, the motion estimation was made on the dim target to make accumulation along the estimated direction in order to enhance the signal of the dim small target. Experiments show that the proposed ring perturbation correction method can effectively improve the local signal-to-noise ratio (SNR) of dim small targets; in sequence image detection, the proposed algorithm in this paper achieves better detection results than other algorithms, and can effectively detect dim small targets in strong clutter background.

A Three-Dimensional Hough Transform-Based Track-Before-Detect Technique for Detecting Extended Targets in Strong Clutter Backgrounds.

Hough Transform (HT), which has a low sensitivity to local faults and good ability in suppressing noise and clutters, usually applies to trajectory detection in a cluttered environment. This paper describes its application for detecting the trajectories of extended targets in three-dimensional measurements, i.e., a two-dimensional positional information and its measuring time. For taking the full merits of a multi-scan, the measuring time is regarded as a variable for the time axis. This correspondence extends the HT to 3-dimensional data. Meanwhile, a three-dimensional accumulator matrix is built for the purpose of voting. The voting process is done in an iterative way by selecting the 3D-line with the most votes and removing the corresponding measurements in each step. The three dimensional Hough Transform-based extended target track-before-detect technique (3DHT-ET-TBD), proposed here, is suitable to track the extended target and non-extended target simultaneously and few false alarm trajectories arise. Both the real data and simulated data are exploited to evaluate its performance. Compared with the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter based methods and a 4DHT-TBD algorithm, the 3DHT-ET-TBD is a more promising approach for multi-extended target tracking problems due to its high efficiency and low computation, especially in situations where the noise and false alarms are considerably high but few measurements are generated by the extended targets.